Notes from Barkan
Activation, onboarding, and what we learn shipping an AI guide that onboards every user.

When your AI support agent should stop talking
The useful support agent is not the one that keeps every conversation automated. It is the one that recognizes its limit and hands over the work without making the customer start again.
Gabriel Lancelot
September 4, 2026

Your AI agent's approval prompt is a permission boundary
Confirm everything and users stop reading. Confirm only the goal and consent becomes dangerously broad. The useful boundary sits at the exact action that changes the world.

Maxence Rabrais
August 29, 2026

The second-workflow problem: why activation dies after the first win
Signup is instrumented to death. The moment that decides retention happens later, when a user tries the real thing your product is for — and nobody is watching.

Maxence Rabrais
August 22, 2026

Why Barkan reads the screen, not the docs
Documentation describes the product in general. The DOM describes it for this user, right now. A look inside how Barkan turns a live page into something a model can act on.

Gabriel Lancelot
August 22, 2026

Nobody reads your documentation — and your activation rate proves it
Your docs are not bad. They are in the wrong place, written at the wrong altitude, and read at the wrong moment. Here is the anatomy of the gap — and the four behaviors that close it.

Maxence Rabrais
August 21, 2026
“Most users don't want another answer. They want to be shown the way, or they want it done. That is the whole product.”
Gabriel Lancelot
Co-founder, Barkan
